Research map / Video / Action recognition
Actions ~ Transformations
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Represent each action as a learned precondition-to-effect transformation | VGG-16 Two Stream action recognition · UCF101 | accuracy (fusion): 91.4% -> 92.4% | Helped |
| Represent each action as a learned precondition-to-effect transformation | VGG-16 Two Stream action recognition · HMDB51 | accuracy (fusion): 58.5% -> 62.0% | Helped |
| Combine transformation-model and Two Stream classification outputs | HMDB51 action recognition · HMDB51 | accuracy (fusion): 62.0% -> 63.4% | Helped |
| Represent each action as a learned precondition-to-effect transformation | Two Stream action recognition · ACT, 43-class classification | accuracy (fusion): 78.7% -> 80.6% | Helped |
| Represent each action as a learned precondition-to-effect transformation | Two Stream action recognition · ACT, cross-category generalization | accuracy (fusion): 63.2% -> 65.5% | Helped |
| Classify first and second video halves independently instead of learning their transformation (ablation) | Two Stream action recognition · UCF101 split 1 | accuracy (fusion): 90.9% -> 90.0% | Hurt |
| Add Softmax loss to force precondition and effect representations into different classes (ablation) | Transformation model · Action recognition | performance | No clear effect |
Closest papers by meaning
- Prompt-guided Disentangled Representation for Action Recognition (NeurIPS 2025 · similarity 0.86)
- End-To-End Learning of Action Detection From Frame Glimpses in Videos (CVPR 2016 · similarity 0.85)
- Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition (NeurIPS 2025 · similarity 0.85)
- Latent Action Pretraining from Videos (ICLR 2025 · similarity 0.84)
- Action Detail Matters: Refining Video Recognition with Local Action Queries (CVPR 2025 · similarity 0.84)
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.